Compositional noisy-logical learning
We describe a new method for learning the conditional probability distribution of a binary-valued variable from labelled training examples. Our proposed Compositional Noisy-Logical Learning (CNLL) approach learns a noisy-logical distribution in a compositional manner. CNLL is an alternative to the well-known AdaBoost algorithm which performs coordinate descent on an alternative error measure. We describe two CNLL algorithms and test their performance compared to AdaBoost on two types of problem: (i) noisy-logical data (such as noisy exclusive-or), and (ii) four standard datasets from the UCI repository. Our results show that we outperform AdaBoost while using significantly fewer weak classifiers, thereby giving a more transparent classifier suitable for knowledge extraction.
Yuille, Alan, and Songfeng Zheng. "Compositional noisy-logical learning." In Proceedings of the 26th Annual International Conference on Machine Learning, pp. 1209-1216. 2009.
ACM International Conference Proceeding Series